Hands-on LLM and AI deployment work — building inference gateways (LiteLLM), deploying open-weight and hosted models, and integrating AI voice assistants.
About the Role
Telnyx is hiring a Forward Deployed Engineer based in Bangalore to embed with enterprise customers and architect, build, and ship production communications and AI solutions (voice, messaging, wireless, inference). You will own technical discovery, design POCs, deploy production systems, instrument observability, and collaborate with sales, product, and engineering to deliver customer outcomes at scale.
Job Description
Role
Telnyx is building a local Enterprise Sales Pod in Bangalore and is hiring a Forward Deployed Engineer (FDE) to embed with enterprise customers in India. The FDE will partner with an Enterprise AE to own the technical side of customer engagements — discovery, architecture, POCs, production go-live, and ongoing stabilization.
Key Responsibilities
- Embed with enterprise customers to understand communications workflows, AI use cases, and integration constraints.
- Design and deploy production systems using Telnyx primitives (voice, messaging, numbers, wireless), WebRTC, and Telnyx APIs.
- Build and deploy AI voice assistants and LLM-based systems, including running open-weight models or consuming hosted models via Telnyx Inference (OpenAI-compatible API).
- Deploy and operate an LLM gateway (e.g., LiteLLM) to provide unified routing, load balancing, retries/fallbacks, rate limits, and per-team virtual keys.
- Instrument and govern LLM usage: cost tracking, caching, logging, observability (OpenTelemetry, Langfuse, etc.), and guardrails.
- Implement production observability: metrics, logs, traces, dashboards, and alerting (examples: Prometheus + Grafana, OpenTelemetry, Graylog, ELK).
- Design model routing strategies for real-time voice workloads balancing latency, cost, and quality with sensible fallbacks.
- Make build-vs-buy recommendations between self-hosted open-weight models and hosted frontier APIs, and keep application code portable across both.
- Lead POCs, pilots, and production launches; remain engaged until the solution is live and stable.
- Collaborate with Product and Engineering on roadmap input from field insights, and produce clear documentation and runbooks for handoff.
Requirements
- CS degree or equivalent experience.
- 3+ years building and shipping production software, including being on-call and debugging production incidents.
- Proficiency in multiple languages: Python, Node.js/TypeScript, and Go.
- Practical understanding of model production failure modes: rate limits, timeouts, retries, streaming, token accounting, and concurrency issues.
- Comfortable deploying containerized services on Kubernetes with secrets management, configuration, and upgrades.
- Experience with observability and being paged: Prometheus, Grafana, OpenTelemetry, Graylog, ELK or equivalents.
- High-concurrency experience with Kafka or other message queues/event streams and knowledge of partitioning, consumer groups, and backpressure mitigation.
- Experience designing and building APIs (OpenAPI, REST, GraphQL), auth, rate limiting, versioning, and idempotency.
- Event-driven and cloud-native design instincts.
- Exposure to SIP, WebRTC, or real-time voice/messaging systems.
- Self-sufficient field engineering: able to read code and docs, run discovery with customer engineers, and present to executives.
- Strong written and verbal English communication skills.
- Based in Bangalore or willing to relocate; this is a hybrid role with travel across India.
- Legally authorized to work in India or eligible for sponsorship.
Bonus / Nice-to-haves
- Experience with AI voice assistants, STT/TTS, or LLM-based conversational systems.
- Hands-on production experience with LLM gateways (LiteLLM, Portkey, Kong AI Gateway) including routing, fallback rules, and virtual key management.
- Familiarity with open-weight model landscape and Indic-language/regional models (BharatGPT, OpenHathi, Bhashini, Sarvam AI).
- Experience with inference serving engines (vLLM, SGLang, TGI, Ollama) and sizing GPU capacity for self-hosted models.
- SQL proficiency (Postgres, MySQL, Oracle), ETL and data wrangling experience.
- CI/CD pipeline design and automation experience.
- Background in telecom, CPaaS, or high-growth SaaS; experience with sovereign/on-prem cloud deployments and Indian regulatory frameworks (DPDP Act, data localization, RBI cloud requirements, MeitY guidelines).
- Security mindset: IAM, encryption, audit logging.
Location & Logistics
- Role is based in Bangalore (hybrid) with travel across India. Candidates must be legally authorized to work in India or eligible for sponsorship.