AI/Machine Learning Engineer III
SteerLean Consulting
Bengaluru, Karnataka, IndiaSENIOR
HybridGenerative AIAI Engineering
Job Description
Build and scale GenAI systems at SteerLean.
Responsibilities
- Design, develop, and deploy scalable GenAI applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, and workflow orchestration frameworks.
- Build production-grade AI systems integrating structured and unstructured enterprise data sources.
- Architect and optimize end-to-end AI pipelines including retrieval, embeddings, vector search, prompt orchestration, evaluation, observability, and monitoring.
- Develop AI-powered copilots, assistants, automation workflows, and autonomous agent systems for business-critical use cases.
- Design hybrid AI systems combining deterministic workflows with autonomous agent behaviors.
- Build multi-agent orchestration workflows with tool calling, memory management, and task planning capabilities.
- Implement tracing, telemetry, observability, and monitoring for AI workflows and agent systems.
- Build automated evaluation pipelines, benchmark suites, regression testing frameworks, and synthetic test datasets for GenAI applications.
- Improve system reliability by reducing hallucinations, optimizing retrieval quality, and implementing AI safety and guardrail mechanisms.
- Optimize inference cost, latency, throughput, and scalability of production AI systems.
- Rapidly prototype and iterate on AI workflows based on user feedback, experimentation, and production telemetry.
- Own AI features and systems end-to-end from prototype through production adoption and operational excellence.
- Collaborate closely with business stakeholders, product managers, platform teams, and data engineers to translate ambiguous business problems into scalable AI solutions.
- Mentor junior engineers and contribute to AI engineering best practices, reusable frameworks, and platform standards.
- Stay current with emerging advancements in LLMs, agentic AI, multimodal systems, open-source models, and AI infrastructure ecosystems
- Fast-paced, AI-first engineering environment
- Opportunity to build cutting-edge GenAI platforms and intelligent systems at enterprise scale
- High ownership, rapid iteration, and strong engineering culture
Qualifications
- 6–9+ years of strong software engineering experience, including backend systems, APIs, distributed systems, and production platform development.
- 3+ years of hands-on experience building and deploying production-grade GenAI or LLM-powered applications.
- Strong expertise in Python and modern AI application frameworks.
- Strong understanding of production system design, scalability, resiliency, and observability principles.
- LLM APIs and open-source models
- Retrieval-Augmented Generation (RAG)
- AI agents and tool-calling architectures
- Multi-agent orchestration systems
- Prompt engineering and prompt optimization
- Embedding models and vector databases
- AI evaluation and observability frameworks
- Strong understanding of vector search, semantic retrieval, ranking, chunking strategies, and context optimization.
- Hands-on experience with cloud platforms such as AWS, Azure, or GCP.
- Strong debugging, optimization, and production troubleshooting capabilities.
- Excellent communication skills with the ability to explain complex AI concepts to both technical and non-technical stakeholders.
- Strong problem-solving mindset with the ability to operate effectively in ambiguous and fast-moving environments.
- Proven ability to lead technical initiatives, mentor teams, and drive execution across cross-functional teams.
- Familiarity with inference optimization techniques including caching, routing, batching, quantization, and model serving optimization.
- Knowledge of AI security, prompt injection mitigation, guardrails, and responsible AI practices.
- Exposure to multimodal AI systems (text, image, audio, video) is a plus.
- Prior consulting or client-facing delivery experience is highly desirable.
- Python
- FastAPI
- SQL
- Snowflake
- Streamlit / Gradio / React
- LangChain / LangGraph / LlamaIndex
- OpenAI / Anthropic / Gemini APIs
- Vector Databases (Pinecone, Weaviate, pgvector, FAISS)
- Docker / Kubernetes
Nice to have
- Experience with orchestration tools.
- Background in client-facing roles.
Benefits
- Fast-paced engineering environment.