Job Description
We are looking for a Senior AI Engineer who can design, build, and scale end-to-end AI systems, combining strong foundations in Machine Learning/Deep Learning with hands-on experience in Generative AI (LLMs, RAG, Agentic systems).
This role requires someone who can own problems from idea to production, work closely with leadership, and contribute to building enterprise-grade AI platforms.
Key Responsibilities
Core AI/ML Engineering (Traditional AI)
- Design and develop ML/DL models from scratch for real-world problems
- Handle full lifecycle: data → training → evaluation → deployment → monitoring
- Work with structured/unstructured data, feature engineering, and model optimization
- Build scalable ML pipelines with reproducibility and versioning
Generative AI & LLM Systems
- Build and deploy LLM-powered applications (chatbots, copilots, assistants, etc.,)
- Design and implement RAG pipelines: (Document ingestion, chunking, embeddings, Vector search (FAISS, Pinecone, etc.), Retrieval optimization)
- Implement prompt engineering, evaluation, and optimization
- Work with multi-model setups (OpenAI, Claude, open-source LLMs, Bedrock, etc.)
Agentic Systems & Advanced Architectures
- Design and build AI Agents / Agentic workflows (LangGraph, Langsmith/crewAI, etc.)
- Implement (Tool calling, Planning & reasoning workflows, multi-step decision pipelines)
- Optimize systems for long-horizon tasks and complex reasoning
System Design & Productionization
- Architect scalable AI systems for enterprise use cases
- Build APIs and microservices for AI solutions
- Ensure: (Low latency, High reliability, Cost optimization)
- Work with Docker, Kubernetes, CI/CD pipelines
Observability, Evaluation & Reliability
- Implement monitoring, logging, and tracing (e.g., Langfuse, Prometheus)
- Define evaluation frameworks: (Accuracy, Retrieval quality, Hallucination detection)
- Debug across: (Model, Data, Retrieval, System Layers)
Collaboration & Ownership
- Work directly with AI Lead / CTO / Product teams
- Translate business problems into AI solutions
- Own delivery of POCs → production systems
- Mentor junior engineers and guide best practices
Required Skills & Experience
Experience
- 6–8 years of experience in AI/ML and Gen-AI systems with strong exposure to software engineering
- 4–6 years in traditional ML/DL systems (along with backend systems)
- 2–3 years in Generative AI / LLM-based systems (LLMs, RAG, agentic workflows)
Technical Skills
- Strong programming: Python (mandatory)
- ML/DL frameworks: PyTorch / TensorFlow / Scikit-learn
- LLM frameworks: LangChain / LlamaIndex / LangGraph (preferred)
- Vector DBs: FAISS / Pinecone / Weaviate / OpenSearch
- Cloud: AWS / Azure / GCP (Bedrock / Azure OpenAI preferred)
- APIs: FastAPI / Flask
- DevOps: Docker, Kubernetes, CI/CD
Core Competencies
- Strong understanding of:
- ML fundamentals (bias/variance, optimization)
- NLP and embeddings
- Retrieval systems
- Ability to debug end-to-end AI systems
- Experience in production deployment and scaling
- Strong system design and problem-solving skills
Good to Have
- Experience with:
- Multi-agent systems
- Reinforcement learning
- Knowledge graphs + RAG
- Experience working with large-scale datasets
- Exposure to AI safety, governance, and compliance
What We Expect
- Ability to build systems from scratch (not just use APIs)
- Strong ownership mindset (end-to-end responsibility)
- Ability to handle evolving requirements
- Passion to stay updated with latest AI advancements
