GEN AI,

Hi,Client: MSIGJob TitleGenAI Lead EngineerAbout the RoleWe are looking for a GenAI Lead Engineer to design, deploy, and maintain agentic AI solutions that are safe, scalable, and business ready. You will own end to end delivery from prompt and agent design to data pipelines, model deployment, observability, and rigorous validation partnering with product, architecture, security, and QA to ship AI features that perform reliably in production.*Update - Python Coding Experience is required. Someone who is well versed with understanding and coding Python, make changes add/change rules specially insurance related and redeploy not just create code and deploy - deep expertise in writing, understand, changing, inventing, debug and deploy AI agent using python.What You'll DoSLM Design and Fine TunningCollect, clean, and preprocess domain-specific datasets for SLM training and fine-tuning.Ensure data quality, diversity, and compliance with privacy and security standards.Fine-tune small language models on curated datasets using techniques like LoRA, adapters, orparameter-efficient tuning.Optimize hyperparameters for performance, latency, and resource efficiency.Agent & Prompt ImplementationHelp design and implement agent orchestration (single and multi agent) and function/tool usestrategies.Craft, version, and optimize prompts and system instructions for accuracy, coherence, anddomain alignment.Integrate external tools/APIs and establish content safety guardrails (e.g., policy enforcement, PIIredaction, jailbreak prevention).Implementation, Testing & MaintenanceBuild resilient agent workflows and services; harden reliability with retries, fallbacks, circuitbreakers.Develop automated tests for prompts, tools, and agent behaviors; maintain regression suites andgolden datasets.Operate AI services in production: performance tuning, cost optimization, incident response, anditerative improvement.Data & MLOpsDesign and manage data pipelines for fine tuning and retrieval (RAG), including cleansing,labeling, and governance.Monitor drift, quality, latency, and safety signals; implement model/agent observability andalerting.Quality Assurance & RiskRun structured evaluations of agent outputs (functional, coherence, safety, bias); trackprecision/recall and hallucination rates.Perform risk assessments for agent behaviors and tool actions; document mitigations andapproval workflows.Collaborate with security/compliance to meet regulatory, privacy, and usage policy requirements.Minimum Qualifications14 + years in software/ML engineering, with 2+ years building LLM/SLM/GenAI solutions inproduction.Proficiency in Python (and/or TypeScript) and modern AI orchestration frameworks (e.g., MicrosoftAgent Framework, Google Agent Development Kit, LangChain, Semantic Kernel).Hands on with retrieval augmented generation (RAG), function calling, prompt optimization, andagent design patterns.Experience building data pipelines (batch/stream), and managing datasets for training/fine tuning andevaluation.Practical understanding of AI guardrails: content filtering, safety policies, redaction, rate limiting, andmisuse prevention.Strong willingness to learn advanced agent orchestration and MLOps practices.Preferred QualificationsMLOps fluency: model packaging, CI/CD, experiment tracking (e.g., MLflow), deployment oncloud/container platforms.IaC (e.g., Terraform/Bicep) and DevOps tooling (e.g., GitHub Actions/Azure DevOps); strong grasp ofobservability.Experience with multi agent systems, toolformer patterns, and complex orchestration graphs.Knowledge of vector databases and retrieval systems; evaluation frameworks (e.g., Ragas, DeepEval)and custom metrics.Familiarity with privacy, compliance, and model risk management practices for AI.Background in tuning open source and hosted models; comfort with hybrid cloud environments.Tools & TechnologiesPython; TypeScript; MAF/Google ADK/LangChain/Semantic Kernel; Vector DBs and frameworks (e.g.,Qdrant/FAISS/Pinecone); CI/CD (GitHub Actions/Azure DevOps); IaC (Terraform/Bicep); Observability(OpenTelemetry/Prometheus); Experiment tracking (MLflow); Cloud AI services (e.g., Azure AI FGoundry, Azure OpenAI, GCP Vertex AI, AWS Bedrock); Containers (Docker/Kubernetes).Working ModelPartner with Product, Architecture, Security, and QA to plan, design, and ship safe AI features.Contribute to internal prompt standards, evaluation datasets, and reuseable components.Document designs, decisions, and risks; mentor peers and champion responsible AI practices.Regards,K P Team Lead RecruitmentsDirect: +1 609 775 9549 Ext: 137 | Email :Wall Street Consulting Services, LLC | |