AI Engineer
On-site · Bengaluru, Karnataka, India
Job Summary
Hands-on AI Engineer needed to drive design, development, and innovation of AI capabilities within an enterprise-grade AI platform. Responsibilities span AI solution design, development, and deployment for Generative AI, Agentic AI, NLP, and related workflows. Build production-ready, large-document RAG workflows, multi-agent systems, and modular Python APIs (with tools such as FastAPI/Flask). Collaborate with backend and cloud teams to ensure performance, cost, and security constraints; optimize inference pipelines and monitor token usage. Act as an internal AI product evangelist, shaping AI concepts and roadmaps, leading internal PoCs and demos, and staying current with evolving tools and techniques. Required skills include 3–5+ years in applied AI/ML, experience with multi-agent orchestration (A2A, ACP, MCP), building advanced RAG pipelines, engineering agent skills, MCP servers, LLM orchestration tools (LangChain, LlamaIndex, LangGraph, CrewAI, AutoGen, Semantic Kernel), vector storage (FAISS, Qdrant, Pinecone, Weaviate, Azure AI Search), strong Python API development (FastAPI/Flask), experience with major LLM providers (OpenAI, Azure OpenAI, Claude, Hugging Face), Azure AI familiarity, prompt/context engineering, and exposure to experiment-tracking tools and DL/NLP/CV toolkits. The role is based in Bengaluru, India with on-site work at the technology campus.
Required Qualifications
- 3–5+ years in applied AI/ML engineering with demonstrated delivery of production Generative and Agentic AI solutions
- Ability to build AI solutions across Generative AI and Agentic AI, including training and fine-tuning language models when required and deploying them for inference
- Proven experience building Agentic AI systems — multi-agent orchestration, reusable agent skills/tools, and agent interoperability (A2A, ACP, MCP)
- Hands-on experience designing and shipping advanced RAG pipelines in production — including hybrid retrieval, re-ranking, query transformation, and systematic evaluation — over large, unstructured document collections
- Hands-on experience building and orchestrating agent skills — authoring and managing reusable skill definitions (e.g., skills.md/Claude Skills-style capability files) that can be dynamically discovered and invoked by LLMs
- Experience building custom MCP (Model Context Protocol) servers — exposing tools, resources, and data sources to LLMs/agents through standardized, interoperable interfaces
- Proven experience building entity extraction and document understanding solutions at scale across diverse, unstructured document formats
- Practical experience with LLM orchestration frameworks and vector/retrieval systems (e.g., LangChain, LlamaIndex, LangGraph, CrewAI, AutoGen, Semantic Kernel; FAISS, Qdrant, Pinecone, Weaviate, Azure AI Search — or equivalents)
- Strong proficiency in Python, including API development (FastAPI/Flask), async/concurrent programming, data wrangling, and rapid prototyping (Streamlit, Gradio, etc.)
- Hands-on experience integrating at least one major LLM provider (e.g., OpenAI, Azure OpenAI, Anthropic/Claude, Hugging Face, Cohere, Meta Llama)
- Solid grasp of prompt engineering, context engineering, and latency-vs-cost trade-offs
- Working familiarity with the Azure AI ecosystem (Azure AI Studio/Foundry, Azure OpenAI, Azure AI Services such as Vision, Translator, and Document Intelligence) — or willingness to ramp up quickly
- Experience with the Anthropic/Claude ecosystem (Claude Skills, Claude Code, Agent SDK)
- Familiarity with fine-tuning and model optimization techniques (PEFT, LoRA, quantization, distillation, pruning)
- Preferred Qualifications: Experience with experiment tracking and evaluation tools (e.g., LangSmith, MLflow); Familiarity with deep learning / classical ML libraries (PyTorch, TensorFlow, Scikit-learn) and CV/NLP toolkits (Transformers, spaCy, OpenCV); exposure to computer vision is a plus; strong Kaggle/AI hackathon background a plus
- Collaboration & Integration: Partner with Full Stack Developers to translate AI capabilities into usable, well-documented APIs; coordinate with DevOps/Cloud Engineers; participate in design reviews and planning for production handoff
- What You'll Bring: builder's mindset; full-spectrum capability to select GenAI, agents, deep learning, or classical ML; product intuition; collaborative spirit; curiosity
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.