Lead Software Engineer Agentic AI Platform & AI Research

Role Overview

We are looking for a highly skilled Senior Software Engineer / Lead Engineer to build and scale enterprise-grade Agentic AI platforms and GenAI solutions. The ideal candidate should have hands-on experience designing, deploying, and operating production AI systems, with strong expertise in Python, Agentic AI, RAG, Distributed Systems, Cloud-Native Engineering, and AI Governance.

You will play a key role in building secure, scalable, and reliable AI platforms that combine LLM capabilities with enterprise-grade controls, observability, governance, and automation.

Key Responsibilities

Agentic AI & Platform Engineering

• Design and develop production-grade Agentic AI workflows and multi-agent systems.
• Build reliable agent runtimes with planning, orchestration, tool execution, memory, approvals, and recovery mechanisms.
• Implement structured outputs, tool/function calling, workflow orchestration, and deterministic execution patterns.
• Define engineering best practices for scalable and governed AI systems.

RAG, Memory & Context Management

• Design and implement enterprise-scale RAG solutions.
• Build memory and context-management capabilities across AI workflows.
• Optimize retrieval quality using embeddings, hybrid search, reranking, and citation grounding.

AI Governance & Reliability

• Implement controls for prompt injection, hallucinations, PII protection, RBAC, tenant isolation, and policy enforcement.
• Establish monitoring, evaluation, observability, and auditability for production AI systems.
• Drive performance tuning, reliability, testing, incident management, and cost optimization.

Cloud & Platform Engineering

• Build and operate scalable AI services using Python, Docker, Kubernetes, and CI/CD.
• Develop enterprise integrations and MCP-based tool interfaces.
• Implement observability using logs, metrics, monitoring, and distributed tracing.

Mandatory Skills

• 6-8 years of software engineering experience with strong backend development expertise.
• 2+ years of hands-on experience building and operating GenAI / Agentic AI applications in production.
• Strong Python development experience using FastAPI, Pydantic, AsyncIO, APIs, and microservices architecture.
• Experience with OpenAI, Azure OpenAI, Anthropic Claude, or Google Gemini.

• Strong experience in:

• Agentic AI Architectures
• Multi-Agent Systems
• Tool/Function Calling
• Workflow Orchestration
• MCP (Model Context Protocol)

• RAG Frameworks

• Hands-on experience with:

• Embeddings
• Vector Databases
• Hybrid Retrieval & Reranking

• Memory & Context Management

• Strong understanding of:

• Distributed Systems
• Concurrency
• Idempotency
• Fault Tolerance

• Failure Recovery

• Experience with:

• PostgreSQL
• Redis and/or MongoDB
• Docker & Kubernetes

• CI/CD Pipelines (GitHub Actions, GitLab CI, etc.)

• Strong knowledge of:

• API Design
• Testing Automation
• Code Quality
• Observability
• Production Operations

Preferred Skills

• Experience with LangGraph, CrewAI, AutoGen, Semantic Kernel, OpenAI Agents SDK, DSPy, or Google ADK.
• Exposure to LLMOps and AI Observability tools such as Langfuse, TrueFoundry, Arize Phoenix, Ragas, DeepEval, or Promptfoo.
• Experience with AI Governance and Security frameworks such as Presidio, Guardrails AI, NeMo Guardrails, OPA, or Cedar.
• Experience with AWS, Azure, or GCP.
• Exposure to BFSI, Insurance, Healthcare, or other regulated industries.