Job Description
Ovii's Interpretation of the Role
Strategic Deployment Engineer at Sarvam, based in Delhi, leads end‑to‑end AI stack deployments in on‑prem, air‑gapped and other constrained environments. The role owns technical delivery, client outcomes and operational hand‑over while collaborating with enterprise accounts.
Role Snapshot
- End‑to‑end AI stack deployment
- Technical SPOC for enterprise accounts
- On‑prem, air‑gapped and constrained environment expertise
- Client outcome ownership (CSAT, uptime, risk flagging)
- Production‑grade Python, Docker, Linux, CI/CD experience
Must-Have Requirements
- Python
- Docker
- Linux systems administration
- REST APIs
- CI/CD pipelines
- LLM inference stacks (vLLM, TGI, Ollama)
- RAG architectures & vector stores
- On‑prem and air‑gapped deployment experience
- software or ML engineering
- full‑cycle on‑prem deployment
Nice-to-Have Signals
- MCP server experience
- Agentic framework familiarity
- Strategic or complex enterprise account experience
- Open‑source project contributions
- Side‑product or entrepreneurial technical craft
- strategic or complex enterprise accounts
- agentic frameworks
Work Setup
- Location: Delhi, India
- Work mode: ONSITE
- Employment type: Full-Time
Not Specified in JD
- Visa sponsorship
- Salary range
- Remote eligibility
- Education requirement
- Certifications
- Relocation
- Travel
- Security clearance
- Coding test
- Portfolio
- GitHub
- Writing sample
- Cover letter
What You'll Likely Work On
- Own full lifecycle deployment of Sarvam’s AI stack in on‑prem, air‑gapped and classified client environments
- Serve as the technical single point of contact for assigned accounts from scoping through steady‑state operations
- Diagnose and resolve integration, model‑drift, inference and infrastructure failures without escalation
- Manage deployment pipelines, model serving and environment configuration in non‑standard, constrained settings
- Drive client‑side adoption via documentation, training and operational hand‑over, and monitor CSAT, time‑to‑value and uptime
Good Fit If You Have
- Thrives in ambiguous, high‑pressure environments and takes ownership of outcomes
- Proven ability to ship and maintain reliable systems end‑to‑end under strict reliability constraints
- Experience navigating ambiguous client requirements and making autonomous technical decisions
Skills
- Python
- Docker
- Linux systems administration
- REST APIs
- CI/CD pipelines
- LLM inference stacks (vLLM, TGI, Ollama)
- RAG architectures & vector stores
- On‑prem and air‑gapped deployment