Sarvam AI Series A
Forward Deployed Engineer
Bengaluru On-site Entry (0-2 yrs) Added Jun 16
About the role
Position: Forward Deployed Software Engineer | 2-5 years. Location: Bengaluru. Type: Full Time, On-Site. Sarvam builds sovereign AI infrastructure for India across research, models, and applications, partnering with major enterprises and institutions, backed by leading venture firms. The role involves architecting production-grade solutions using generative AI and agentic systems. Candidates work directly with customers and product teams to deliver real production implementations rather than prototypes. Multiple openings exist across four product teams: Samvaad, API Dashboard, Content Studio, and ARYA. Samvaad: build and deploy conversational AI agents across voice, WhatsApp, and web channels; manage client engagements from kickoff through production deployment, troubleshoot agent performance, and iterate based on usage data. API Dashboard: develop developer tooling, integrations, and open-source plugins; own the complete developer experience from API design through documentation. Content Studio: deploy dubbing and translation APIs into production environments; serve as primary technical contact for clients, prototype solutions, and build managed service delivery pipelines. ARYA: build Model Context Protocol servers and multi-agent infrastructure; design event-driven data pipelines, work with databases at scale, and architect coordinated agent systems. Required Qualifications: 2-5 years shipping production systems; strong Python proficiency across the stack; deep LLM knowledge including context windows, embeddings, RAG, tool calling, prompt design; experience designing multi-agent architectures with memory management; ability to design evaluation frameworks and quality metrics for AI systems; high agency, able to unblock yourself and figure things out without supervision. Preferred Experience: production AI agent deployments; open-source contributions or shipped side projects; customer-facing engineering roles; LLM orchestration framework expertise; voice/speech model experience; familiarity with Sarvam's products.
Industry
AI / LLM / Enterprise AI
Top skills for this role
- LLM/agent architecture (RAG
- multi-agent
- eval pipelines)
- 2. Python fluency and production systems engineering
- 3. LLM orchestration frameworks (LangChain
- LangGraph
- CrewAI)
Languages
Python (strong fluency required)
Frameworks & tools
LangChainLlamaIndexCrewAILangGraphGoogle ADKMCP serversKafkaSQSRabbitMQSQL and NoSQL databases
AI / ML skills
Deep LLM/agent understanding (context windowstokensembeddingsRAGtool callingprompt designfailure modes)multi-agent architecture design (memory managementorchestration)eval pipeline setupvoice/speech models (TTSSTTASR) as bonus
Customer skills
Customer-facing engineering roles preferred; high agency and self-unblocking mindset
Domain knowledge
AI-native product development; voice/speech domain a bonus
You'll be redirected to Sarvam AI's career page.
Want to be matched directly?
Join the network