Technical capabilities required
- Must have strong knowledge of APIs and tools like Postman for testing and debugging.
- Basic coding knowledge in Python, JavaScript, or Java.
- Hands-on experience with prompt engineering — writing, testing, and optimizing prompts for AI tools (like GPT or Claude).
- Understanding of how AI models, SDKs, and integrations work in production.
- Good to have experience in data visualization tools like Amplitude or Grafana.
- Excellent debugging, analytical, and documentation skills.
- Familiarity with LLM behavior, prompt chaining, and evaluating AI output quality is a big plus.
What Would You Do :
- Collaborate with the sales, customer success, and engineering teams to understand user needs and translate them into effective AI prompts and workflows.
- Design and iterate on prompt templates for different customer use cases to improve accuracy, tone, and reliability of AI responses.
- Analyse AI performance, identify gaps, and fine-tune prompts or input structures to deliver better results.
- Maintain and update internal prompt libraries and AI agent configurations.
- Partner with the engineering team to test AI features, debug prompt issues, and provide structured feedback for model improvement.
- Work with Ops teams to ensure customer-facing AI agents behave consistently and deliver high-quality responses.
- Create internal documentation and training resources to help other teams use and improve prompts effectively.
Who Should Apply :
- 4–8 years of experience in technical, customer engineering, or AI-related roles.
- Strong curiosity about AI, LLMs, and how prompt design affects AI performance.
- Excellent written communication and analytical thinking.
- Technical background with the ability to test, debug, and interpret API or SDK outputs.
- Highly organized, detail-oriented, and comfortable managing multiple priorities.
- Experience collaborating across cross-functional teams (engineering, product, and customer success).
- Bonus: prior experience working with OpenAI, Anthropic, LangChain, or RAG-based systems.
Why 100ms
- You’ll be part of a small, fast-growing, engineering-first startup shaping the future of AI + video collaboration.
- Work alongside engineers who’ve built large-scale video and AI systems at Facebook and Hotstar.
- Freedom to experiment, learn, and lead AI innovation within the team.
- Solve real-world problems at the intersection of real-time communication and AI at scale.
Additional Information
- At 100ms, we place a strong emphasis on in-office presence to promote collaboration and strengthen company culture. Under the current policy, employees are expected to work from the office at least three days a week—Tuesday, Wednesday, and Friday—as an essential part of their role.
Top Skills
What We Do
100ms AI builds voice-first AI agents for healthcare operations, automating high-friction workflows like scheduling, intake, benefits verification, prior authorization, and telehealth coordination.
We combine deep expertise in real-time communications with healthcare-grade AI infrastructure to help care teams scale with empathy, precision, and compliance. Our agents are designed to be safe enough for clinical use, human enough to build trust, and flexible enough to adapt to any workflow, from solo clinics to large health systems.
Previously known for powering real-time video in platforms across EdTech, fitness, and virtual events, 100ms is now focused on transforming healthcare operations through conversational AI that works in the real world.
Founded in 2020, we are a team of engineers, clinicians, and operators committed to building the future of healthcare conversations.
