Senior AI Engineer

Were Hiring

Job title: Senior AI Engineer

Location: Bangalore

Experience: 5+ Years

Notice Period: Immediate- 15 Days

AI ENGINEER - SENIOR LEVEL

Position Overview

We are seeking a Senior AI Engineer to lead the design, development, and deployment of advanced Generative AI systems, including sophisticated multi-agent workflows, production-grade RAG implementations, and enterprise-scale AI applications. This role requires deep technical expertise combined with the ability to mentor team members and drive architectural decisions.

Must-Have Skills & Experience

Experience Requirements:

• 5-8 years of professional experience in AI/ML Engineering, Data Science, or Software Engineering with AI focus
• Proven track record of delivering 5+ production AI systems from conception to deployment
• Experience leading technical workstreams or mentoring junior engineers
• Demonstrated ability to troubleshoot complex AI system failures and performance issues

Core Technical Skills:

• Advanced Python: Expert-level Python with strong software engineering fundamentals (design patterns, SOLID principles, testing)
• LLM Orchestration: Deep expertise in LangChain, LangGraph, and at least one other framework (LlamaIndex, Haystack)
• Agentic AI: Hands-on experience building multi-agent systems with planning, reasoning, tool-use, and memory capabilities
• Advanced RAG: Expertise in retrieval optimization including:
• Embedding model selection and comparison
• Hybrid search strategies (dense + sparse retrieval)
• Re-ranking techniques (Cohere, ColBERT, cross-encoders)
• Query reformulation and expansion
• Metadata filtering and structured retrieval
• Vector Databases: Production experience with vector database optimization, indexing strategies (HNSW, IVF), and performance tuning
• Cloud Platforms: Strong experience deploying and scaling AI workloads on Azure, AWS, or GCP
• Semantic caching implementation
• Synthetic data generation for training/evaluation
• Specific foundation model expertise (GPT-4, Claude, Gemini, Llama)
• Guardrails and safety frameworks

Agent Architecture:

• Expert knowledge of agent orchestration patterns including state machines, ReAct, and planning frameworks
• Experience implementing scratchpad reasoning and chain-of-thought prompting
• Knowledge of tool routing, dynamic tool selection, and API orchestration
• Experience building memory systems (short-term, long-term, episodic)

System Design & MLOps:

• Experience designing scalable AI architectures for enterprise applications
• Strong understanding of observability, logging, and tracing for AI systems (LangSmith, LangFuse, Weights & Biases)
• Knowledge of prompt versioning and evaluation pipelines
• Experience with CI/CD for ML systems
• Understanding of cost optimization strategies for LLM applications

Data Engineering:

• Experience building data pipelines for AI applications
• Knowledge of data preprocessing, transformation, and quality assurance
• Familiarity with both SQL and NoSQL databases

Good-to-Have Skills

Multi-Agent Expertise:

• Production experience with LangGraph, CrewAI, or AutoGen for multi-agent orchestration
• Knowledge of agent communication protocols and coordination patterns
• Experience with hierarchical agent structures and delegation patterns

Advanced AI Techniques:

• Experience with fine-tuning foundation models (LoRA, QLoRA, full fine-tuning)
• Knowledge of model quantization and optimization techniques
• Familiarity with function calling and structured output parsing
• Experience with streaming and real-time AI applications

Evaluation & Testing:

• Expertise in LLM evaluation frameworks (RAGAS, TruLens, UpTrain)
• Experience designing golden test sets and benchmark suites
• Knowledge of human-in-the-loop evaluation methodologies
• Experience with A/B testing and experimentation frameworks

Enterprise AI:

• Deep understanding of AI governance, compliance, and responsible AI
• Experience implementing security controls (PII redaction, access controls, audit logging)
• Knowledge of enterprise architecture patterns and integration strategies
• Familiarity with on-premises deployment and air-gapped environments

Document Intelligence:

• Advanced experience with document parsing, OCR (Azure Document Intelligence, Textract)
• Knowledge of layout-aware chunking and document understanding
• Experience with table extraction and multimodal document processing

Certifications:

• Azure AI Engineer Associate or Expert
• AWS Certified Machine Learning - Specialty
• Google Cloud Professional ML Engineer
• Certified Kubernetes Application Developer (CKAD) - bonus

Domain Expertise:

• Experience with finance, accounting, ERP systems, or healthcare applications
• Industry-specific AI application experience

Key Responsibilities

• Lead end-to-end ownership of AI feature streams from design to production
• Design and implement sophisticated multi-agent workflows with complex orchestration logic
• Build evaluation frameworks and establish quality benchmarks for AI systems
• Troubleshoot production issues and optimize system performance (latency, cost, accuracy)
• Mentor mid-level and junior engineers through code reviews and pair programming
• Collaborate with architects and product teams on technical roadmaps
• Create technical documentation, runbooks, and knowledge transfer materials
• Drive best practices for prompt engineering, testing, and deployment

Deliverables

• Production-grade multi-agent systems with comprehensive error handling and recovery
• Evaluation harnesses with automated regression testing
• Performance optimization reports (latency benchmarks, cost analysis)
• Technical architecture documents and system design specifications
• Mentorship and knowledge transfer sessions for team members

Educational Requirements

• Bachelor's degree in Computer Science, Engineering, Mathematics, or related field
• Master's degree preferred OR equivalent experience with strong portfolio of AI projects

Soft Skills

• Excellent problem-solving and debugging skills
• Strong communication abilities - can explain complex systems to both technical and non-technical audiences
• Leadership qualities with experience guiding technical discussions
• Ability to make pragmatic trade-offs between perfection and delivery
• Proactive approach to identifying and resolving technical debt
• Collaborative mindset with focus on team success