Senior ML Engineer

Bot Consulting; Jaipur; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Bot Consulting is seeking an experienced ML/AI engineer to design, build, and deploy Generative AI applications on Amazon Bedrock in a high-security, multi-tenant AWS environment.

You will architect agentic and multi-agent systems, create robust retrieval/search pipelines, and own the SageMaker lifecycle from training to deployment and monitoring.

Qualifications

• BS/MS in CS/Engineering/Math or equivalent experience.
• 5–8+ years in ML/AI engineering, with at least 3 years AWS experience.
• At least 1 year of production-grade Generative AI/LLM experience.
• Experience with client-facing engagements and architectural sessions.
• Ability to work across time zones with strong ownership.

Responsibilities

• Design, build, and deploy Generative AI apps on Amazon Bedrock (RAG, summarisation, classification).
• Architect multi-agent systems using Bedrock, Step Functions, Lambda.
• Build retrieval solutions with embeddings, vector search, and grounding.
• Own SageMaker lifecycle: training, deployment, registry, CI/CD, drift detection.
• Develop AI evaluation, observability, and human-in-the-loop workflows.
• Implement guardrails, PII handling, and responsible AI controls.
• Design secure, scalable AWS architectures and IaC (CDK/CloudFormation/Terraform).
• Lead discovery sessions, architecture reviews, and client presentations.
• Mentor engineers and contribute reusable accelerators.

Skills

Generative AI

AWS Bedrock

Agentic AI

Retrieval & Search

SageMaker & MLOps

AI Evaluation

AWS Data Stack

AWS Architecture & Security

Programming & Engineering

Classical ML & NLP

Education

Bachelor's or Master's in CS/Engineering/Math

Tools

LangChain

Bedrock Agents SDK

LangGraph

MCP server development

Job description

Role & responsibilities

• Design, build, and deploy Generative AI applications on Amazon Bedrock, including RAG, document intelligence, summarisation, classification, and assistant-style solutions.
  
• Architect and implement agentic and multi-agent systems using Bedrock, AWS Step Functions, Lambda, and related AWS services.
  
• Build retrieval solutions using embeddings, hybrid keyword/vector search, Amazon OpenSearch, pgvector, relevance tuning, reranking, citation, and grounding.
  
• Own the Amazon SageMaker lifecycle, including feature engineering, training, tuning, model registry, deployment, MLOps, retraining, drift detection, and CI/CD.
  
• Build AI evaluation and observability frameworks using golden datasets, LLM-as-judge, regression testing, error taxonomies, tracing, and human-in-the-loop workflows.
  
• Implement AI guardrails, prompt-injection defences, PII handling, and responsible AI controls for regulated and data-sensitive use cases.
  
• Build and integrate AI data foundations using S3, Glue, Spark, Redshift, Athena, DMS, Kinesis, and Firehose.
  
• Design secure, multi-tenant, scalable, and cost-aware AWS architectures using IAM, Lake Formation, VPC, PrivateLink, API Gateway, EKS, ECS, Fargate, and Lambda.
  
• Define infrastructure as code using AWS CDK, CloudFormation, or Terraform and deliver through CI/CD.
  
• Estimate, monitor, and optimise AI and data workload costs, including model selection, token economics, caching, compute, and storage.
  
• Lead technical discovery, requirements sessions, architecture discussions, client presentations, and executive readouts.
  
• Contribute through code reviews, reusable accelerators, internal engineering patterns, and mentoring of engineers.

Requirements

Technical Requirements

• Generative AI & AWS: Hands-on experience with Amazon Bedrock, foundation models, RAG, Knowledge Bases, Guardrails, function calling, LLM gateways, and model selection based on quality, latency, cost, and data residency.
  
• Agentic AI: Experience building tool-using and multi-agent systems using Bedrock, Step Functions, Lambda, Bedrock Agents/AgentCore, Strands Agents SDK, and MCP.
  
• Retrieval & Search: Strong experience with Amazon OpenSearch, vector/hybrid search, embeddings, BM25, reranking, pgvector, and end-to-end RAG including document parsing, chunking, grounding, and retrieval evaluation.
  
• SageMaker & MLOps: Experience with SageMaker training, tuning, deployment, Model Registry, Pipelines, monitoring, drift detection, CI/CD, and fine-tuning open-weight models including LoRA.
  
• AI Evaluation & Responsible AI: Experience with golden datasets, LLM-as-judge, regression testing, prompt engineering, guardrails, prompt-injection protection, PII handling, human-in-the-loop workflows, and LLM observability.
  
• AWS Data Stack: Strong knowledge of S3, Glue, Spark, Redshift, Athena, DMS, Kinesis, Firehose, Aurora PostgreSQL, DynamoDB, QuickSight, and lakehouse technologies such as Iceberg/Delta Lake.
  
• AWS Architecture & Security: Experience with IAM, Lake Formation, VPC, PrivateLink, EKS/ECS/Fargate, Lambda, API Gateway, infrastructure as code, CI/CD, monitoring, and cost optimisation.
  
• Programming & Engineering: Expert Python with pandas, NumPy, scikit-learn, PyTorch, boto3, and pytest; strong SQL, Git, Docker, and Linux skills, with FastAPI/backend and Streamlit/React familiarity.
  
• Classical ML & NLP: Strong foundation in statistics, supervised/unsupervised ML, time-series forecasting, demand/supply planning, and NLP including classification, entity extraction, topic modelling, and free-text analysis.
  

Requirements

• Bachelors or Master’s degree in Computer Science, Engineering, Statistics, Mathematics, a related quantitative field, or equivalent demonstrated experience.
  
• 5–8+ years of experience in machine learning engineering, data science, or AI engineering, including at least 3 years of hands-on AWS experience.
  
• At least 1 year of production-grade Generative AI/LLM experience, including a system taken to production or a client-accepted POC that you can explain in architectural detail.
  
• Demonstrated experience working directly with external clients or business stakeholders and independently leading technical sessions.
  
• Experience working effectively across significant time-zone differences with strong self-direction and ownership.
  
• Excellent written and spoken English, with the ability to create clear architecture documentation and present to senior audiences.
  
• AWS Certified Machine Learning and Anthropic certification, held or committed to within 60 days of joining, as applicable.
  

Preferred Qualifications

• AWS Certified Solutions Architect – Professional.
  
• Consulting, professional services, systems integrator, or AWS Partner experience, with familiarity with utilisation, scoping, and statement-of-work realities.
  
• Experience in healthcare/life sciences, financial services, insurance, manufacturing/supply chain, or compliance/legal technology.
  
• Experience with LangChain, LangGraph, LlamaIndex, CrewAI, Strands Agents SDK, Bedrock AgentCore, or MCP server development.
  
• Experience with knowledge graphs, Amazon Neptune, GraphRAG, Snowflake, dbt, Apache Airflow, Databricks, Amazon Connect, or contact-centre AI.
  
• Open-source contributions, publications, conference talks, AWS Community Builder, or AWS Hero experience.
  

Certification Requirements

• AWS Certified Machine Learning — Specialty or current designated AWS ML certification: Required (at hire or within 60 days)
  
• Anthropic certification: Preferred (at hire or within 60 days)
  
• AWS Certified Solutions Architect – Professional: Strongly Preferred
  
• AWS Certified Data Engineer – Associate, AWS Certified AI Practitioner, AWS Certified Security – Specialty: Advantageous