Sr. AI Engineer

Viamagus Technologies; Hyderabad; On-site; INR 4,000,000 - 6,500,000; Full time

Job summary

Viamagus Technologies Pvt. Ltd. in Hyderabad is seeking a Senior AI Engineer to build production-grade GenAI applications and lead client-facing solutioning for Fortune 500 clients.

You will design LLM copilots, RAG pipelines, and agentic workflows, deploying on major cloud platforms with strong CI/CD, monitoring, and governance. This is a founding role shaping a new AI practice. The position emphasizes hands-on engineering (about 70%) and client-facing work (about 30%), with opportunities to

Qualifications

• 4–7 years of software engineering with real production systems.
• Python mastery in production-grade Python (FastAPI or similar).
• Production GenAI experience with at least one real LLM-powered feature: prompt design, structured outputs, tool/function calling, streaming.
• RAG engineering with embeddings and vector databases (Pinecone, Weaviate, pgvector, or Qdrant).
• Agentic systems: build agents or workflows with LangGraph, LangChain, or LlamaIndex; MCPs and agent SDKs.
• Full-stack capability: TypeScript/React/Next.js; ship a working product.
• Cloud AI deployment: hands-on with AWS Bedrock, Azure AI Foundry, or GCP VertexAI, plus Docker and CI/CD.
• Evaluation & trust: eval harnesses, observability, responsible handling of PII and guardrails.
• Client-facing communication: run a workshop, scope, demo to stakeholders, articulate ROI.

Responsibilities

• Design and build production GenAI applications, LLM copilots, and RAG pipelines.
• Engineer retrieval end-to-end: chunking, embeddings, vector stores, retrieval, re-ranking, and hybrid search.
• Build agents/workflows with LangGraph/LangChain; integrate MCP servers and agent SDKs.
• Augment enterprise platforms with predictive insights, intelligent automation, and conversational UX.
• Deploy to AWS Bedrock, Azure AI Foundry, or GCP Vertex AI with CI/CD and observability.

Skills

Python mastery

Client-facing communication

English proficiency

Tools

LangGraph

LangChain

LlamaIndex

MCP servers

agentSDKs

Pinecone

Weaviate

pgvector

Qdrant

LangSmith

Langfuse

Arize

Job description

JobTitle:SeniorAIEngineerGenAISolutions

Location:Hyderabad,India|EmploymentType:Full-Time|Experience:47Years| Reportsto:AIPracticeLead

AboutViamagus

Viamagus Technologies Pvt. Ltd. is a technology and talent solutions company helping organizations build high-impact engineering and AI capabilities. We are hiring on behalf of a fast-growing AI-first technology services company with delivery teams across the US and India, serving enterprise and Fortune 500 clients across financial services, healthcare, insurance, retail, and SaaS. The client is building a brand-new AI Consulting & Engineering practice, helping enterprises turn the platforms they already run into intelligent, AI-enabled systems tied to measurable business outcomes.

PositionSummary

We're looking for a Senior AI Engineer who does two things exceptionally well: builds production-grade GenAI applications, and sits in front of clients to shape what gets built. Expect roughly 70% hands-on engineering and 30% client-facing solutioning. You'll take AI use cases from discovery workshop to deployed, monitored production system LLM copilots, RAG pipelines, and agentic workflows that live inside enterprise clients' products and platforms. This is real production work for enterprise and Fortune 500 clients, not disconnected proofs of concept. You'll be one of the founding engineers of this practice.

KeyResponsibilities

• DesignandbuildproductionGenAIapplicationsLLMcopilots,RAGpipelines,agenticworkflows andAI-nativeUX—onamodern2026AIstack
• Engineerretrievalendtoend:chunking,embeddings,vectorstores,retrieval,re-ranking,andhybrid search;debugretrievalqualitywhenitmatters
• Buildagentsandmulti-stepworkflowswithLangGraphand LangChain;integrateMCPservers andagentSDKsfortoolaccess
• Augmententerpriseplatformswithpredictiveinsight,intelligentautomation,andconversationalUX
• DeploytoAWSBedrock,AzureAIFoundry,orGCPVertexAIwithsolidCI/CD,observability,andguardrails
• Buildevaluationharnesses,wireupLLMobservability,andbakeinresponsible-AIbasics:PIIhandling, guardrails,andaudittrails
• Runclientdiscoveryworkshopsandtranslatebusinessproblemsintoscoped,ROI-backedAIusecases
• Demoworkingsoftwaretotechnicalandbusinessstakeholders,anddefenddesign decisionsand tradeoffs
• Contributetoreusableacceleratorsandmentorjuniorengineersasthepracticegrows

RequiredSkillsMandatory

• 4–7yearsofsoftwareengineeringexperiencewithrealproductionsystems
• Pythonmastery—clean,testable,productionPython(FastAPIorsimilar)
• ProductionGenAIexperience—shippedatleastonerealLLM-poweredfeature: promptdesign, structuredoutputs,tool/functioncalling,streaming
• RAGengineering—chunking,embeddings,vectordatabases (Pinecone,Weaviate,pgvector,orQdrant), retrieval,re-ranking,hybridsearch
• Agenticsystems—builtagentsorworkflowswithLangGraph,LangChain,orLlamaIndex;understandsMCPandagentSDKs
• Full-stackcapability—TypeScript/React/Next.js,abletoshipaworkingproduct,notjustanAPI
• CloudAIdeployment—hands-onwithAWSBedrock,AzureAIFoundry,orGCP VertexAI,plus DockerandCI/CD
• Evaluation&trust—evalharnesses,LLMobservability(LangSmith,Langfuse,orArize),responsible handlingofPIIandguardrails
• Client-facingcommunication —canrun aworkshop,scopeause case,demoto stakeholders,and articulate ROI;fluentwrittenandspokenEnglish

Preferred

• ExperienceaddingAItoenterpriseplatformssuchasClarityPPM,Medallia,ServiceNow,or SalesforceEinstein
• DeeperMLOps—MLflow,Weights&Biases,modelmonitoring,serverlessGPU

NicetoHave

• Data&RAGinfrastructure—ETL/ELT,CDC,orchestration,streaming,knowledgegraphs,Databricksor Snowflake
• Fine-tuning&multimodalexperience—LoRA,distillation,vision/voice/multimodalapplications
• Industrydomaindepthinfinancialservices,insurance,healthcare,orretail
• AIgovernanceawareness(NISTAIRMF,EUAIAct)andrelevantcloudAI/MLcertifications

ExperienceRequired

• 4 - 7 years of softwareengineeringexperience, includingdemonstratedproduction GenAI,RAG, andagentic systemswork

WhyJoin

• Foundingrole—helpshapethearchitecture,standards,andcultureofanewAIpractice withrealautonomy
• Production,notpilots—shipAIthatgoesliveforenterpriseandFortune500clients
• Outcomesoverhype—everyengagementistiedtoabusinessKPI
• Modernstack,realdepth—workacrossleading2026AItoolingwithateamthatshipstoproduction
• Mentorshipandgrowth—learndirectlyfromseniorfull-stackandAIleadership