Develop and deploy traditional ML, Generative AI, RAG, and agentic applications. Responsibilities include designing AI systems, building APIs and end-to-end ML pipelines, leveraging AWS and Azure services, optimizing retrieval performance, implementing evaluation and observability, and supporting production deployments. The role collaborates with technical and business stakeholders across experiments, pilots, and scalable solutions.
Huron is a global consultancy that collaborates with clients to drive strategic growth, ignite innovation and navigate constant change. Through a combination of strategy, expertise and creativity, we help clients accelerate operational, digital and cultural transformation, enabling the change they need to own their future.
Join our team as the expert you are now and create your future.
- Design and develop AI-powered systems using both traditional ML and Generative AI techniques, including prompt engineering, fine-tuning, embeddings, and Retrieval-Augmented Generation (RAG) architectures
- Build intelligent applications and agentic systems that can perform tasks autonomously or interactively, using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or similar
- Architect and implement end-to-end RAG pipelines, including document ingestion, chunking strategies, embedding generation, vector indexing, hybrid search, and contextual response generation
- Develop modular, well-documented APIs and service components (e.g., using FastAPI or Flask) to enable model integration and consumption
- Design, build, and manage end-to-end AI pipelines, including data ingestion, transformation, validation, model training, inference, deployment, and knowledge retrieval workflows
- Leverage AWS and Azure AI/ML services (e.g., Bedrock, SageMaker, Azure OpenAI, Azure ML, Document Intelligence, vector databases, etc.) to accelerate development and deployment
- Implement observability, evaluation, and monitoring mechanisms to track model accuracy, drift, retrieval quality, grounding fidelity, reliability, and task-level reasoning
- Optimize RAG systems for latency, scalability, cost efficiency, and response quality in production environments
- Collaborate with software engineers, data scientists, solution architects, and business stakeholders to ensure seamless solution design and transition to production
- Support both rapid experimentation (POCs, pilots) and robust, scalable deployments, depending on the maturity of each use case
- Stay up to date with emerging trends in Generative AI, AI agents, orchestration frameworks, RAG evaluation techniques, and continuous improvement methodologies
- 4 to 6 years of hands-on experience in AI/ML development or intelligent application engineering
- Strong proficiency in Python and familiarity with modern ML/AI libraries (e.g., scikit-learn, PyTorch, TensorFlow, OpenAI APIs)
- Hands-on experience designing and deploying RAG-based systems, including embeddings, vector databases (e.g., FAISS, Pinecone, Chroma, Azure AI Search), and retrieval optimization techniques
- Experience building APIs or backend services using FastAPI, Flask, or equivalent frameworks
- Exposure to agent frameworks (e.g., LangGraph, AutoGen) and multi-agent orchestration patterns
- Experience with orchestration standards or tools such as MCP or agent routing protocols is a plus
- Familiarity with cloud platforms (AWS, Azure) and containerization tools (Docker)
- Hands-on experience with cloud-based ML platforms such as Azure Machine Learning, AWS SageMaker, or Google AI/ML services
- Experience with MLOps pipelines, CI/CD for model delivery, RAG evaluation frameworks (e.g., RAGAS), or model monitoring is a plus
- Knowledge of AI system evaluation, observability, prompt performance testing, and grounding validation is a plus
- Ability to work on cross-functional teams, balance multiple projects, and communicate effectively with technical and non-technical audiences
- Cloud certifications in AI/ML services (Azure, AWS, or Google Cloud) are a plus
- Bachelor’s degree in Computer Science, Engineering, Data Science, or a related field
Huron Chennai, Tamil Nadu, IND Office
Chennai, India
Similar Jobs
Information Technology
Designs, develops, deploys, and monitors AI and machine learning solutions, including predictive models, NLP applications, LLMs, generative AI, RAG systems, copilots, chatbots, and virtual assistants. Responsibilities include building ML pipelines, creating APIs and microservices, integrating AI with enterprise and cloud platforms, applying MLOps practices, and ensuring model scalability, security, governance, compliance, and reliability.
Top Skills:
Ai/MlAPIsCloud PlatformsGenerative AiLarge Language Models (Llms)MicroservicesMlopsNatural Language Processing (Nlp)Retrieval-Augmented Generation (Rag)
Retail • Sports
Build and operate production-grade LLM applications, agentic workflows, RAG and retrieval pipelines, AI memory architectures, and evaluation harnesses. Deploy and monitor AI services using cloud infrastructure, containers, APIs, and MLOps platforms. Configure AI gateways, manage model routing and costs, secure integrations, and optimize serving architectures. Collaborate with product, engineering, SRE, security, and software teams to deliver scalable AI capabilities.
Top Skills:
AWSAzureCi/CdCpusDeepevalDockerEmbedding ModelsGCPGpusGraph DatabasesGraphQLGrpcIamIn-Memory DatabasesJavaKubernetesLangchainLanggraphLlamaindexMilvusMlflowModel Context ProtocolPgvectorPineconePythonQdrantRagRagasRestRustTypescriptVector DatabasesWeights & Biases
Security • Cybersecurity
Designs, builds, evaluates, and deploys production-grade autonomous and multi-agent AI systems for cybersecurity detection and response. Develops LLM orchestration, tool use, memory, planning, RAG pipelines, evaluation frameworks, and scalable agent infrastructure. Optimizes reliability, latency, accuracy, cost, observability, and failure recovery while partnering with security researchers and product teams.
Top Skills:
AnthropicAutogenCrewaiFaissGeminiHeliconeHugging FaceLanggraphLangsmithLlmsOpenaiOpentelemetryPgvectorPineconePythonRagWeaviate
What you need to know about the Chennai Tech Scene
To locals, it's no secret that South India is leading the charge in big data infrastructure. While the environmental impact of data centers has long been a concern, emerging hubs like Chennai are favored by companies seeking ready access to renewable energy resources, which provide more sustainable and cost-effective solutions. As a result, Chennai, along with neighboring Bengaluru and Hyderabad, is poised for significant growth, with a projected 65 percent increase in data center capacity over the next decade.
