Forward Deployed Engineer

Location: Pune, Chennai, Delhi, Bengaluru, Kolkata, Hyderabad, Mumbai, Gurugram, Coimbatore, Noida, Bhubaneswar  •  Level: Mid Level  •  Openings: 2  •  Type: Full-time
Apply on GO Jobs

Job description

1. Job Details
Job Title: Forward Deployed Engineer
Job Location: Bangalore/Hyderabad/Chennai/Pune/Mumbai /Noida/Kolkata
2. Candidate Expectations
Total Experience and Relevant Experience – 4–12 years
Candidate Location : Bangalore/Hyderabad/Chennai/Pune/Mumbai /Noida/Kolkata
Skills –  LLMs, RAG, AI Agents and Vector Databases, LangGraph, LangChain, LlamaIndex, Semantic Kernel , Evals, MCP, A2A and multi-agent architectures, Docker, Kubernetes and CI/CD
Candidate Industry (BPO / KPO / GBS / GCC / GSS / Captive Shared Services)
Diversity – N/A
3. Education and Certification
Qualification: Mandatory: BE/B.Tech/MBA/BCA/MCA
Specific Remarks: Distance education not accepted, 15 years regular stream mandatory, etc.
4. Detailed Job Description
Key Responsibilities:
Work closely with clients to understand business problems and translate them into AI/ML solutions.
Build AI Agents, RAG applications and multi-agent workflows.
Develop LLM-powered applications using Python and modern AI frameworks.
Design RAG pipelines covering document processing, embeddings, vector search, retrieval and generation.
Build LLM evaluation (Evals) frameworks to measure accuracy, relevance, hallucination, latency and cost.
Develop tool calling, API integrations and agent workflows.
Rapidly prototype PoCs and convert successful solutions into production-grade applications.
Implement prompt/context engineering, guardrails, observability and responsible AI.
Deploy solutions on Azure/AWS/GCP and work with enterprise security and engineering teams.
Troubleshoot and continuously improve AI solutions based on real-world production feedback.
5. Key Skills : Mandatory Key Skills:
  • Strong hands-on Python and AI/ML experience.
  • Practical experience with LLMs, RAG, AI Agents and Vector Databases.
  • Experience with LangGraph, LangChain, LlamaIndex, Semantic Kernel or similar frameworks.
  • Understanding of LLM Evals, prompt engineering and AI observability.
  • Experience with REST APIs, FastAPI, Git and cloud platforms.
  • Strong problem-solving and client-facing communication skills.
  • Ability to work in an ambiguous, fast-paced environment and deliver working solutions quickly.
  • Experience with MCP, A2A and multi-agent architectures.
  • Experience with Azure OpenAI, AWS Bedrock or Google Vertex AI.
  • Experience with enterprise GenAI implementations.
  • Knowledge of Docker, Kubernetes and CI/CD.
  • Experience in Life Sciences, Healthcare or other regulated industries.
6.Good to Have Skills: N/A

Job ID: 2046