Back to list

Vacancy description

Senior Engineering Manager (Agentic AI) in India, भारत

Rekruton Technologies

Rs 30 - 50 lakhs p.a.

India, भारत

The Role

We are seeking an execution-driven Senior Engineering Manager to own the technical architecture, system reliability, and end-to-end delivery of our Agentic AI voice testing product line.

In this role, you will lead multiple cross-functional PODs consisting of:

  • AI/ML Engineers (Multi-agent orchestration, MCP server architectures, LLM evaluation & tracing pipelines, STT/TTS streaming, synthetic caller persona generation)

  • Full-Stack / Web Developers (Enterprise SaaS dashboards in React/Next.js, Python/FastAPI microservices, real-time analytics, workflow builders, API integrations)

  • QA / SDETs (Telecom call verification, regression frameworks, deterministic and non-deterministic test automation)

Your primary mandate is predictable roadmap execution, architectural rigor, and operational discipline. You must be hands-on enough to audit system designs, review critical code, and bridge the gap between probabilistic generative AI workflows and deterministic, enterprise-grade delivery schedules.

Key Responsibilities
1. Multi-Pod Leadership & Predictable Delivery

  • Direct and mentor multiple cross-functional engineering PODs (AI/ML, Full-Stack/Backend, QA/SDET), establishing high ownership, code quality, and engineering hygiene.

  • Run disciplined Agile cadences (sprint planning, effort estimation, architectural reviews, retrospectives) to guarantee on-time delivery of quarterly roadmap commitments.

  • Identify and eliminate cross-pod dependencies, technical debt, and single points of failure through clear architectural documentation (RFCs/ADRs) and rigorous code reviews.

2. Agentic AI Architecture & Observability

  • Guide the technical design and scaling of multi-agent conversational workflows (dynamic intent exploration, multi-turn memory/context management, tool calling, RAG pipelines, and autonomous task execution) built on LangChain, LangGraph, and MCP (Model Context Protocol) servers.

  • Oversee multi-model integration strategies across commercial (GPT, Claude, Gemini) and open-source LLMs, balancing response latency, accuracy, and inference cost.

  • Enforce production-grade AI observability, tracing, and evaluation pipelines using tools like Langfuse, ensuring every release is benchmarked against hallucination, behavioral drift, and regression metrics.

3. Full-Stack Platform, Telephony & AI Governance

  • Oversee scalable, asynchronous backend services (Python, FastAPI) and modern web front-ends (React, https://jobeax.com/link/Z30sZYC3jcRenVso), backed by relational, NoSQL, caching, and vector/search datastores (PostgreSQL, MySQL, MongoDB, Redis, OpenSearch/Elasticsearch, Vector DBs).

  • Architect real-time, event-driven audio and conversational pipelines integrating telephony and messaging protocols (SIP, WebRTC, RTP, Asterisk, Twilio, WebSockets, WhatsApp Business APIs).

  • Establish strict AI governance and application security protocols—covering prompt injection defenses, MCP tool permissions, data privacy, and auditability across enterprise customer environments.

4. Quality Engineering & Organizational Growth

  • Partner with QA leadership to automate end-to-end regression, synthetic call-load testing, and deterministic verification over non-deterministic AI outputs.

  • Champion a high-trust, asynchronous, remote-first engineering culture across distributed teams in India, driving hiring, career progression, and performance management.

What We Are Looking For
Leadership & Execution

  • 11–16 years of software engineering experience, including 3–5+ years leading multiple engineering teams or cross-functional pods across the full SDLC.

  • Proven ability to step into complex, fast-moving codebases, establish architectural visibility, and drive predictable delivery timelines without sacrificing engineering quality.

  • Strong command of engineering metrics (DORA, sprint predictability, MTTR, escape defect rates) and practical sprint management for AI/R&D-heavy workloads.

Core Technical Stack & Applied AI

  • Agentic AI & LLM Orchestration: Deep, practical understanding of multi-agent systems, tool-calling, context/memory management, RAG, and evaluation pipelines using LangChain, LangGraph, Langfuse, and MCP servers.

  • Backend & Frontend Architecture: Strong foundation in Python (FastAPI, async programming), microservices, event-driven architectures, and working familiarity with React and Next.js.

  • Data & Search Infrastructure: Hands-on architectural familiarity with PostgreSQL, MySQL, MongoDB, Redis/ElastiCache, Elasticsearch/OpenSearch, and Vector Databases.

  • Cloud & DevOps: Solid experience deploying and monitoring containerized workloads on AWS (and/or Azure) using Docker, Kubernetes, and CI/CD pipelines.

  • AI Security & Governance: Practical awareness of model oversight, auditability, RBAC, MCP server permissions, and prompt injection mitigation.

Domain Advantage (Strongly Preferred)

  • Direct exposure to voice AI, conversational bots, IVR systems, and telecom/VoIP infrastructure (SIP, WebRTC, RTP, Asterisk, Twilio, real-time audio streaming, or CCaaS platforms).

  • Experience building automated testing, QA assurance, or synthetic simulation platforms.

Loading similar vacancies…