Senior GenAI Engineer
First seen by Alion on Sep 22, 2026.
Role : Senior Gen AI Engineer
Candidate must have a minimum 10 years experience of which past 2 years must be in Generative AI.
Key Responsibilities :
1. GenAI Application Development & Deployment :
- Develop scalable, asynchronous microservices using Python (FastAPI) for chatbots, copilots, and agentic workflows.
- Design event-driven architectures to support high concurrency, rate limiting, and real-time responsiveness.
- Implement secure, versioned REST/gRPC APIs.
- Use Pydantic, dependency injection, and modular coding practices for maintainability.
- Proficient in working with databases using ORMs like SQLAlchemy.
- Ensure observability using logging, metrics, tracing, and health checks.
- Create responsive React.js frontends integrated via REST APIs or WebSockets.
- Deploy applications on Cloud Run, GKE, using Docker, Artifact registry, CI/CD pipelines.
2. LLM-Powered Conversational Interfaces :
- Design and build LLM-powered chatbots, voicebots, copilots and other applications using LangChain or custom orchestration frameworks.
- Integrate enterprise-grade LLM APIs (Gemini, OpenAI, Claude) for multi-turn, intelligent interactions.
- Implement user session management and context/state tracking for personalized and continuous conversations.
- Build RAG pipelines with vector databases, knowledge graphs to ground responses with external knowledge and documents.
- Apply advanced prompt engineering (ReAct, Chain-of-Thought with tool calling) for precise and goal-oriented outputs.
- Ensure performance in low-latency, streaming environments using WebSockets, gRPC, and SIP media gateways.
- Perform fine-tuning of open-source LLMs (LLaMA variants) using techniques like SFT, LoRA, for cost-effective domain adaptation.
- Optimize high-speed inference pipelines leveraging multi-GPU clusters (up to 8x H100s) to reduce latency and improve throughput.
3. Multi-Agent Systems & Orchestration :
- Create multi-agent systems & Implement orchestration patterns like supervisor-agent, hierarchical, and networked agents using frameworks like ADK, Pydantic AI and LangGraph.
- Use LangGraph for stateful workflows with memory, conditional branching, retries, and async execution.
- Enable persistent context and long-term memory.
- Monitor behavior, drift, and performance using observability tools.
- Skilled in developing agents with ADK and A2A protocols & experienced in configuring custom and remote MCP servers.
Tech Stack :
- LLMs & Agents : OpenAI (GPT-4), Claude, Gemini, Mistral, LLaMA 3.2/4.
- Databases : BigQuery, Redis, FAISS, Pinecone, SQLAlchemy, Chroma, GCP Vector search.
- Protocols/APIs : REST, gRPC, WebSockets, OAuth2, OpenAPI, MCP, A2A.
- DevOps : Docker, GitHub Actions, Jenkins, GKE, Cloud Run.
- Infra & Tools : GCP, Azure, Pub/Sub, Artifact Registry, NGINX, Langfuse, Postman, Pytest.
Skills
Python, Generative AI, LangChain, FastAPI, LangGraph, Artificial Intelligence, LLM, ORM