Build and operate backend services and infrastructure for LLM- and voice-driven healthcare applications. Implement APIs, productionize LLM workflows, deploy cloud containerized services, and monitor performance and reliability end-to-end.
We’re building the next generation of conversational voice and video AI for life sciences—intelligent with 100% regulatory compliance. Our AI medical experts help pharma teams engage doctors, support patients, and unlock insights faster than ever before. We’ve just raised our seed, signed our first customers, and are scaling fast. If you're excited about building real-world AI in an early stage startup and shape not just our product, but our identity and culture —this is your moment.
We move like owners. Everyone at SynthioLabs has the autonomy and the responsibility to drive projects, challenge decisions, and push things forward. We don’t wait for permission. If you see a gap, you fill it. If you see a better way, you try it.
We ask “why” until we get to the root. We explore new ideas, research papers, every single edge case and anything that sharpens our understanding.
We use AI like a second brain. From writing code to writing docs, debugging flows to exploring new ideas, AI is part of our daily rhythm. Everyone here gets hands-on with the tools, learns how to prompt better, and treats AI as a teammate.
Synthio is looking for a hands-on Software Engineer who enjoys building end-to-end systems and shipping production-grade products. This role sits at the intersection of backend engineering, AI systems, and infrastructure. You’ll work on LLM-powered and voice-enabled applications, integrate external APIs, and own services from design through deployment and operation.
You’ll join a small, fast-moving team building real-world software for healthcare and pharma, where reliability, performance, and correctness are non-negotiable. We value engineers who take ownership, move quickly, and are comfortable operating across the stack.
- Build and maintain backend services that power AI- and LLM-driven products
- Design and implement APIs, data flows, and service integrations
- Productionize LLM-based workflows (prompting, retrieval, orchestration, evaluations)
- Deploy and operate services with a focus on low latency, high availability, and robustness
- Design and manage infrastructure (containerization, cloud services, CI/CD)
- Work on voice-enabled systems (STT/TTS, streaming APIs) as part of end-user experiences
- Monitor, debug, and optimize systems for performance, reliability, and cost
- Collaborate closely with founders and product stakeholders to turn ambiguous requirements into scalable software
- Own features and services end-to-end, from initial design to production support
- 2–5 years of experience in software engineering or backend-focused roles
- Strong proficiency in Python
- Experience designing and building APIs and backend systems
- Hands-on experience working with LLM APIs (OpenAI, Anthropic, or similar)
- Comfort with cloud infrastructure and DevOps fundamentals (Docker, AWS ECS/EKS/Lambda, observability, basic security)
- Interest in AI-powered systems, including voice and conversational interfaces
- Solid systems and architecture thinking, with a pragmatic approach to tradeoffs
- Ability to work with incomplete specs and make sound engineering decisions independently
At Synthio, we build software that directly supports patients, physicians, and pharma teams. This is production software, not prototypes or demos. The systems you build will be used in real workflows, under real constraints, and at real scale. You’ll have meaningful ownership and a clear line of sight from your code to real-world impact.
- Competitive salary
- Remote-friendly
- Team offsites in San Francisco
Similar Jobs
Database
Build and own Supabase’s AI tooling, including agents, MCP servers, agent skills, dashboard assistants, and developer-facing AI capabilities. Establish eval-first development through benchmarks, instrumentation, quality KPIs, and regression gates. Design how documentation and product knowledge are exposed to agents, create reusable AI patterns, and collaborate across Docs, CLI, Frontend, SDK, and infrastructure teams. Improve reliability, testing, authentication, hosting, and developer experience in a fast-moving, globally distributed environment.
Top Skills:
BraintrustEdge FunctionsEs ModulesJavaScriptJavascript BundlersMcpNpmPgvectorPostgresTypescriptVector Embeddings
Web3
Develop AI-focused quality engineering solutions for LLM applications, copilots, chatbots, RAG pipelines, and autonomous agents. Build evaluation frameworks, synthetic datasets, and scalable Python automation for UI, API, microservice, and distributed-system testing. Validate AI safety, groundedness, hallucinations, agent workflows, vector search, tool integrations, observability, reliability, and performance. Integrate quality workflows into CI/CD and cloud environments while collaborating with Engineering, AI/ML, Platform, Product, and DevOps teams.
Top Skills:
Ai AgentsAutogenAWSAzureAzure DevopsChromadbCi/CdClaudeCrewaiCypressDistributed SystemsDockerEmbeddingsFaissGeminiGithub ActionsGithub CopilotGitlab Ci/CdGoogle Cloud PlatformGraphQLJenkinsKubernetesLangchainLanggraphLlamaindexLlmsMcpMicroservicesObservabilityOpenai SdksOracle Cloud InfrastructurePineconePlaywrightPythonQdrantRagRestRobot FrameworkSeleniumSemantic KernelSQLVector DatabasesWeaviate
Internet of Things • Mobile • Retail
Build and deploy production-grade Generative AI, RAG, and agentic AI applications for enterprise use cases. Responsibilities include designing retrieval and multi-agent pipelines, developing Python APIs and microservices, integrating Azure and enterprise systems, implementing evaluations, LLMOps, security guardrails, identity controls, observability, and CI/CD. The role also requires rapid prototyping, troubleshooting, architecture documentation, stakeholder collaboration, and converting validated concepts into secure, scalable production solutions.
Top Skills:
Agentic AiAutogenAzureAzure Ai FoundryAzure Ai SearchAzure DevopsAzure Key VaultAzure Machine LearningAzure OpenaiBicepCosmos DbDockerFastapiFlaskGitGitGithub ActionsJSONJwtKubernetesLangchainLanggraphLangsmithMicrosoft Semantic KernelMlflowModel Context Protocol (Mcp)Oauth 2.0Openai ApisOpenid ConnectOpentelemetryPgvectorPineconePlaywrightPostgresPytestPythonQdrantRbacRedisRest ApisRetrieval-Augmented Generation (Rag)SsoTerraformWeaviate
What you need to know about the Chennai Tech Scene
To locals, it's no secret that South India is leading the charge in big data infrastructure. While the environmental impact of data centers has long been a concern, emerging hubs like Chennai are favored by companies seeking ready access to renewable energy resources, which provide more sustainable and cost-effective solutions. As a result, Chennai, along with neighboring Bengaluru and Hyderabad, is poised for significant growth, with a projected 65 percent increase in data center capacity over the next decade.
