@alokbishoyi97: deployed and served custom models for a big @evo__hq customer over the past week insane and rapid learnings understood …
Summary
A developer shared their experience deploying and optimizing custom AI models for a customer over a week, using posttraining, inference tuning, and orchestration, and promoted services for high-spending AI workloads.
View Cached Full Text
Cached at: 09/02/26, 06:00 PM
deployed and served custom models for a big @evo__hq customer over the past week
insane and rapid learnings
understood their traffic patterns, setup evals - did lot of ablation runs on multiple models
eventually we weren’t getting enough savings, so we posttrained a model - first SFT and then other RL policies
then came inference optimization setup end to end , including custom spec dec models as per their data distribution, tuning vLLM configs, quantization etc
then more work around compute allocation , inference capacity planning / warming up as per traffic profiles etc
all orchestrated by our in house autoresearch / AI engineer
all this to ensure our customers get best bang for buck
we are now rapidly onboarding inference providers who can reliably service our growing demand
and if you are someone whose agentic/AI workload spends are more than $20k a month, then do reach out. We would love to figure what we could do for you!
Similar Articles
@svpino: This looks pretty interesting: An end-to-end system to build, evaluate, deploy, monitor, and continuously improve your …
Santiago Valdarrama highlights an end-to-end system for building, evaluating, deploying, and monitoring specialized AI models, noting that enterprises are willing to pay for custom small models despite the popularity of foundation models.
@rhythmrg: https://x.com/rhythmrg/status/2066561780495896785
The article argues that enterprises should post-train their own custom AI models for mission-critical, high-volume use cases to achieve differentiation, cost savings, and control over tradeoffs, rather than relying solely on general frontier models.
@heyshrutimishra: Most teams are spending 10x on models that stopped learning the day they shipped. Rented models don't improve with your…
Shruti Mishra promotes Oumi, an open-source AI platform that lets teams own and continuously improve models with their data, contrasting with rented APIs that don't learn.
@akshay_pachaar: Serverless vs on-prem vs edge deployment. (read before your next deploy) These are three different answers to the same …
This article compares serverless, on-prem, and edge deployment for AI models, highlighting inefficiencies in current multi-model serving. It introduces the Superlinked Inference Engine (SIE), an open-source tool that serves multiple models on a single GPU by dynamically loading and unloading weights, aiming to reduce costs and complexity.
@PrajwalTomar_: I genuinely did not expect this to work this well. I hired an AI employee at the agency this week. It runs on an open-s…
A user shares surprise at how well an open-source AI agent works for client research using Hyperagent, which lets you swap between models like Kimi K2.6, GLM 5.2, DeepSeek V4, and Qwen 3.7.