Vacancy description

Staff Software Engineer - AI Engineer in Bangalore, भारत

Tekion

Bangalore, भारत

About Tekion:

Positively disrupting an industry that has not seen any innovation in over 50 years, Tekion has challenged the paradigm with the first and fastest cloud-native automotive platform that includes the revolutionary Automotive Retail Cloud (ARC) for retailers, Automotive Enterprise Cloud (AEC) for manufacturers and other large automotive enterprises and Automotive Partner Cloud (APC) for technology and industry partners. Tekion connects the entire spectrum of the automotive retail ecosystem through one seamless platform. The transformative platform uses cutting-edge technology, big data, machine learning, and AI to seamlessly bring together OEMs, retailers/dealers and consumers. With its highly configurable integration and greater customer engagement capabilities, Tekion is enabling the best automotive retail experiences ever. Tekion employs close to 3,000 people across North America, Asia and Europe.

About Tekion:

Positively disrupting an industry that has not seen any innovation in over 50 years, Tekion has challenged the paradigm with the first and fastest cloud-native automotive platform that includes the revolutionary Automotive Retail Cloud (ARC) for retailers, Automotive Enterprise Cloud (AEC) for manufacturers and other large automotive enterprises and Automotive Partner Cloud (APC) for technology and industry partners. Tekion connects the entire spectrum of the automotive retail ecosystem through one seamless platform. The transformative platform uses cutting-edge technology, big data, machine learning, and AI to seamlessly bring together OEMs, retailers/dealers and consumers. With its highly configurable integration and greater customer engagement capabilities, Tekion is enabling the best automotive retail experiences ever. Tekion employs close to 3,000 people across North America, Asia and Europe.

Why This Role Matters

This role powers Tekion’s AI‑native, end‑to‑end automotive platform by turning unified dealership data across DMS, CRM, Digital Retail, Service, and Payments into real‑time intelligence. You’ll operationalize a graph‑based contextual ecosystem so agents can retrieve the right context, enforce policy, and personalize experiences that drive measurable dealer outcomes. You’ll also build the resilient control layer - MCP and the LLM Gateway - that enables safe, cost‑efficient, multi‑provider LLM usage. Finally, you’ll define the standards for building, evaluating, deploying, and governing agentic systems so product teams can ship AI features quickly, safely, and at scale. In addition to enabling agentic systems powered by LLMs, this role also drives building the platform for classical ML models driving optimization across dealership operations. 

What Makes This Opportunity Unique

This role offers direct, measurable impact on dealer outcomes and consumer experiences across Tekion’s Automotive Retail Cloud and Automotive Enterprise Cloud, with end‑to‑end ownership of an LLM control plane and gateway that serve multi‑tenant workloads under SLAs and, quality and cost guardrails. You’ll leverage a rich vertical dataset and domain graph spanning sales, service, parts, F&I, accounting, and consumer touchpoints to power context‑aware agents and retrieval‑augmented generation. You’ll also shape core levers - agent orchestration patterns, evaluation frameworks, and safety guardrails - so improvements in latency, reliability, evaluation quality, and safety translate into dealer KPIs like upsell, cycle time, CSAT, and service revenue. You’ll also maintain and enhance the platform to support classical supervised and unsupervised ML models .

Responsibilities

  • Build and run the LLM control plane/gateway: smart routing, rate limits/quotas, failover, and token/cost tracking.

  • Ship a unified API and SDKs (REST/gRPC) with normalized schemas, structured outputs, caching, and full observability (traces/logs/metrics).

  • Enforce safety and privacy by default: content filtering, prompt/response validation, and PII redaction.

  • Enable multi‑model, multi‑vendor use LLMs with automated canarying and versioning.

  • Own the agent runtime: tool registry, permissions, function calling, grounding, and retrieval.

  • Design orchestration patterns (sequential, planner‑executor, streaming) and manage agent state and long‑running workflows.

  • Enabling platform components for training and scoring pipelines for classical ML (e.g., XGBoost/LightGBM/linear/trees) and deep models; standardize experiment tracking and packaging.

  • Create components to Monitor model and data drift, retraining and tuning models as needed to maintain accuracy and relevance.

  • Add human‑in‑the‑loop review and safe‑actioning before agents touch dealer systems.

  • Evolve the domain graph and entity resolution; build reliable data ingestion pipelines.

  • Serve real‑time context to agents (profiles, inventory, pricing, appointments, service history) with access controls and lineage.

  • Power retrieval with hybrid search (graph + vector + keyword) and smart cache/TTL to balance accuracy, latency, and cost.

  • Run continuous offline/online evaluations for quality, factuality, bias, and safety for the platform sanity.

  • Define SLOs for latency (p50/p95), uptime, and cost view capabilities; enable autoscaling and spend controls.

  • Maintain a model/agent registry, versioning, approvals, audit trails, and reproducibility; support compliances where needed.

  • Provide templates/CLIs, sandboxes, and docs so product teams can build and ship fast; mentor engineers and champion MLOps and AI safety best practices.

Desired Skills & Experience

  • 8+ years building large‑scale data/ML or platform systems; strong software engineering fundamentals (Abstracted API design, concurrency, distributed systems).

  • Production experience with Python plus one of Java/Scala/Go; microservices and API design.

  • MLOps at scale: pipelines (Airflow/Kubeflow), tracking/registry (MLflow), CI/CD for models, A/B testing, shadow/canary, and online feature computation (Spark/Flink/Kafka).

  • Cloud and containers: AWS (preferred), plus Docker/Kubernetes; performance, reliability, and cost engineering in multi‑tenant SaaS.

  • Practical ML knowledge (feature engineering, training, evaluation, drift detection); experience deploying models that power user‑facing workflows.

  • Built or operated an LLM gateway/control plane: provider adapters, routing/policies, caching, quota/rate‑limit, cost and token accounting.

  • Agentic systems: tool use/function calling, orchestration frameworks, human‑in‑the‑loop, safety/guardrails, and online evaluation/telemetry.

  • Graph and retrieval: knowledge graphs (e.g., Neo4j/Neptune/TigerGraph), GraphQL, vector search (e.g., pgvector/Qdrant/Milvus), hybrid retrieval patterns.

Preferred Mindset

  • Platform‑as‑product: obsess over developer experience, paved roads, and clear SLAs.

  • Thinks in systems - observability, fallback, access control are core, not afterthoughts.

  • Passionate about AI - enjoys enabling real-world LLM and agentic use cases.

  • Cost‑aware builder: you treat latency and dollars as first‑class metrics and design for graceful degradation.

  • Vendor‑agnostic thinker: choose the right model/provider per use case; build for portability and resilience.

  • Documentation and teaching: you make complex systems understandable; you uplevel teams.

Current Tekion Employees: Please apply via the Internal Job Board in Ashby.

Note: Tekion recently transitioned to a new recruiting tool and we appreciate your patience and feedback as we adjust to our new system!

Tekion is proud to be an Equal Employment Opportunity employer. We do not discriminate based upon race, religion, color, national origin, gender (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender identity, gender expression, age, status as a protected veteran, status as an individual with a disability, victim of violence or having a family member who is a victim of violence, the intersectionality of two or more protected categories, or other applicable legally protected characteristics.

For more information on our privacy practices, please refer to our Applicant Privacy Notice here .

Important : Tekion will only contact candidates from an @ https://jobeax.com/link/U6VLsepI2Q6oKh41 email address or through our applicant tracking system ([email protected]). We may also work with authorized recruiting partners from time to time. Tekion and its recruiting partners will never ask you to pay fees or send money for applications, interviews, training, or onboarding. If you receive a message that seems suspicious, please do not respond or share personal or financial information.

Similar vacancies

More like this role

Coupang Internal

Staff Software Engineer

  • Remote
  • Hybrid
  • On-site
  • Contract
  • IT
  • Backend
... analysis, and implement long-term architectural solutions. - Collaborate with engineering leaders across Coupang to establish common platform standards and unlock AI innovation across the organization. Basic Qualifications: - 8+ years of professional software development experience. - 5+ years of experience designing and operating ...

Bangalore, भारत

  • IT
  • Design
  • Fullstack
Staff Software Engineer Sureify is on a mission to modernize the life and annuity insurance industry. Composed of 250+ insurance veterans, technology experts, and creatives, Sureify offers its employees a unique opportunity to advance a powerful industry that has fallen behind digitally. Sureify’s product suite, Lifetime, ...

Hyderabad, भारत

  • Full-time
  • IT
Leadership software engineering role at Cohesity in Bengaluru. Needs 8+ years and a https://jobeax.com/link/wOcGjnRrrRFUZzB4, https://jobeax.com/link/MPrGoo1PSJpZ7d0e or B.Tech. What you'll do - Design and build massively distributed systems at web-scale - Identifying performance bottlenecks and applying performance optimization ...

Bangalore, भारत

  • Full-time
  • IT
Leadership software engineering role at Intuit in Bengaluru. Needs 8+ years and an https://jobeax.com/link/MPrGoo1PSJpZ7d0e, https://jobeax.com/link/2DENLGgQM7whDhaE or B.E.. What you'll do - Drives velocity in the organization by accelerating customer, business, and technology outcomes by identifying and driving key opportunities ...

Bangalore, भारत

Coupang Internal

Staff Software Engineer

  • Remote
  • Hybrid
  • On-site
  • Contract
  • IT
  • Backend
... analysis, and implement long-term architectural solutions. - Collaborate with engineering leaders across Coupang to establish common platform standards and unlock AI innovation across the organization. Basic Qualifications: - 8+ years of professional software development experience. - 5+ years of experience designing and operating ...

Bangalore, भारत

  • Remote
  • Hybrid
  • On-site
  • Full-time
  • IT
... business software processes and interactions, including where AI and automation can add value Responsibility Area: Leadership - Manage individual contributors' daily tasks - Mentor software and AI engineers to ensure high product quality across both deterministic code and AI/model behavior - Perform detailed code reviews, ...

Hyderabad, भारत

  • Full-time
  • IT

Rs 10000 per month

... authentication, push notifications, feature flags, and GraphQL systems. - Mentor engineers, participate in technical reviews and interviewing, and contribute to engineering culture and company initiatives. Requirements - 6+ years of professional software development experience and 8+ years building and shipping native mobile ...

Hyderabad, भारत

  • Remote
  • Hybrid
  • On-site
  • IT
... smarter, faster, and better. We're building an AI-native culture where technology and talent are unstoppable together. And we're just getting started. Join us to put AI to work for people. Job Description About the role We’re looking for a Staff Software Engineer to set technical direction for a team building AI-native products ...

Hyderabad, भारत

  • Remote
  • Hybrid
  • Full-time
  • IT
  • Design

$5.6 USD

... systems, and career sites. About the Role Fivetran is building data pipelines to power the modern data stack for thousands of companies. We’re looking for a Staff Software Engineer for our data pipeline service to build and work on data pipelines that moves data from various sources to data warehouses. The work is very ...

Bangalore, भारत

  • Remote
  • Hybrid
  • On-site
  • Full-time
  • IT
... thinking about how to integrate AI into work processes, decision-making, or problem-solving. This may include using AI-powered tools, automating workflows, analyzing AI-driven insights, or exploring AI’s potential impact on the function or industry. - 9+ years of experience in software engineering, with a track record of delivering ...

Hyderabad, भारत